Power Load Missing Data Imputation Model Based on Dynamic Fusion Attention Mechanism
[1]ZHAO Dong,LI Yarui,WANG Wenxiang,et al.Power Load Missing Data Imputation Model Based on Dynamic Fusion Attention Mechanism[J].Journal of Zhengzhou University (Engineering Science),2025,46(02):111-118.[doi:10.13705/j.issn.1671-6833.2024.05.004]
Copy
Journal of Zhengzhou University (Engineering Science)[ISSN
1671-6833/CN
41-1339/T] Volume:
46
Number of periods:
2025 02
Page number:
111-118
Column:
Public date:
2025-03-10
- Title:
- Power Load Missing Data Imputation Model Based on Dynamic Fusion Attention Mechanism
- CLC:
- TP183
- Abstract:
- In order to improve the imputation accuracy of power load missing value data and guarantee the efficiency of subsequent data analysis and application, firstly, a imputation model based on dynamic fusion of attention mechanism dynamic fusion of attention mechanism imputation model (DFAIM) was proposed. The model consisted of an attention mechanism module and a dynamic weighted fusion module, where the deep correlation between features and timestamps was mined through the two different attention mechanisms of the attention mechanism module. Secondly, feature representations were obtained by assigning learnable weights to the two outputs of the attention mechanism module through the dynamic weighted fusion module. Finally, replacing the values of the missing locations with the obtained feature representations to obtain the imputed values. The proposed model was validated using the meteorological and load dataset and the UCI electric load dataset for an area in New York City, and the experimental results showed that DFAIM had certain advantages in evaluating metrics such as MAE, RMSE, and MRE compared to statistics, machine learning, and deep learning models imputation models.
- References:
-
[1]朱俊丞, 杨之乐, 郭媛君, 等. 深度学习在电力负荷预测中的应用综述[J]. 郑州大学学报(工学版), 2019, 40(5): 13-22. ZHU J C, YANG Z L, GUO Y J, et al. Deep learning applications in power system load forecasting: a survey [J]. Journal of Zhengzhou University (Engineering Science), 2019, 40(5): 13-22.[2]SUO Q L, ZHONG W D, XUN G X, et al. GLIMA: global and local time series imputation with multi-directional attention learning[C]∥2020 IEEE International Conference on Big Data (Big Data). Piscataway: IEEE, 2020: 798-807.[3]LIN W C, TSAI C F. Missing value imputation: a review and analysis of the literature (2006—2017)[J]. Artificial Intelligence Review, 2020, 53(2): 1487-1509.[4]MALARVIZHI M R. K-NN classifier performs better than K-means clustering in missing value imputation[J]. IOSR Journal of Computer Engineering, 2012, 6(5): 12-15.[5]SMOLA A J, VISHWANATHAN S V N, HOFMANN T. Kernel methods for missing variables[J]. Society for Artificial Intelligence and Statistics, 2005: 325-332.[6]徐岩, 张晓, 周兴华, 等. 基于Prophet-LightGBM的台区短期负荷预测方法[J]. 华北电力大学学报(自然科学版), 2024,51(6):13-19.XU Y, ZHANG X, ZHOU X H, et al. The short-term load forecasting method of transformer based on ProphetLightGBM[J]. Journal of North China Electric Power University (Natural Science Edition), 2024,51(6):13-19.[7]张颖超, 成金杰, 邓华, 等. 基于相似日和特征提取的短期风电功率预测[J]. 郑州大学学报(工学版), 2020, 41(5): 44-49.ZHANG Y C, CHENG J J, DENG H, et al. Short-term wind power prediction based on similar day and feature extraction[J]. Journal of Zhengzhou University (Engineering Science), 2020, 41(5): 44-49.[8]CAO W, WANG D, LI J, et al. BRITS: bidirectional recurrent imputation for time series[C]∥Proceedings of the 32nd International Conference on Neural Information Processing Systems. NewYork: ACM, 2018: 6776-6786.[9]VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]∥Proceedings of the 31st International Conference on Neural Information Processing Systems. New York: ACM, 2017: 6000-6010.[10] DU W J, CÔTÉ D, LIU Y. SAITS: self-attention-based imputation for time series[J]. Expert Systems with Applications, 2023, 219: 119619.[11]周远翔, 林孟龙, 陈健宁, 等. 基于自注意力生成对抗网络的电力设备在线监测缺失数据填补[J]. 高电压技术, 2023, 49(5): 1795-1809.ZHOU Y X, LIN M L, CHEN J N, et al. Missing data imputation for online monitoring of power equipment based on self-attention generative adversarial networks[J]. High Voltage Engineering, 2023, 49(5): 1795-1809.[12] JÄGER S, ALLHORN A, BIEßMANN F. A benchmark for data imputation methods[J]. Frontiers in Big Data, 2021, 4: 693674.[13] AHN H, SUN K, PIO KIM K. Comparison of missing data imputation methods in time series forecasting[J]. Computers, Materials & Continua, 2022, 70 (1): 767-779.[14]马思远, 焦佳辉, 任晟岐, 等. 基于注意力机制的城市多元空气质量数据缺失值填充[J]. 计算机工程与科学, 2023, 45(8): 1354-1364.MA S Y, JIAO J H, REN S Q, et al. Missing value filling for multi-variable urban air quality data based on attention mechanism[J]. Computer Engineering & Science, 2023, 45(8): 1354-1364.[15] HAN K, WANG Y H, CHEN H T, et al. A survey on vision transformer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45 (1): 87-110.[16] TRINDADE A. Electricity load diagrams 2011—2014 data set[EB/OL]. (2015-12-03)[2024-08-05]. https: ∥archive. ics.uci. edu/ml/datasets/Electricity Load Diagrams20112014.[17] Microsoft. Neural network intellgence[EB/OL]. (201706-01) [2024-08-05]. https:∥github. com/ microsoft/nni.[18] BERGSTRA J, BENGIO Y. Random search for hyper-parameter optimization[J]. Journal of Machine Learning Research, 2012, 13: 281-305.[19] YOON J, ZAME W R, VAN DER SCHAAR M. Estimating missing data in temporal data streams using multi-directional recurrent neural networks[J]. IEEE Transactions on Biomedical Engineering, 2019, 66 (5): 1477-1490.
- Similar References:
Memo
-
Last Update:
2025-03-13